{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RZIGYO4DI5HBFXANI4RRBKFX2Y","short_pith_number":"pith:RZIGYO4D","schema_version":"1.0","canonical_sha256":"8e506c3b83474e12dc0d472310a8b7d60912d59b4261e53d1edd58139bc1e565","source":{"kind":"arxiv","id":"2404.19543","version":2},"attestation_state":"computed","paper":{"title":"RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yucheng Hu, Yuxing Lu","submitted_at":"2024-04-30T13:14:51Z","abstract_excerpt":"Large Language Models (LLMs) have catalyzed significant advancements in Natural Language Processing (NLP), yet they encounter challenges such as hallucination and the need for domain-specific knowledge. To mitigate these, recent methodologies have integrated information retrieved from external resources with LLMs, substantially enhancing their performance across NLP tasks. This survey paper addresses the absence of a comprehensive overview on Retrieval-Augmented Language Models (RALMs), both Retrieval-Augmented Generation (RAG) and Retrieval-Augmented Understanding (RAU), providing an in-depth"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.19543","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-30T13:14:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac975826572bb67bb20417c392fbc429893d7cd9f258c3a0009f3a4e4ad809a6","abstract_canon_sha256":"1207cbc70cc8d09fed4257c02b9d58a08a6ecf76025ffee33e33da304f596ee4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:58.990835Z","signature_b64":"IZSZ2ocqZTZWifvPX0oP8rKpQokzupDXoLpGuyyZuqx1uOxWqt22rjmvxw5g65I/GwK4V7acLs9HyE3FvRj+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e506c3b83474e12dc0d472310a8b7d60912d59b4261e53d1edd58139bc1e565","last_reissued_at":"2026-07-05T11:28:58.990308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:58.990308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yucheng Hu, Yuxing Lu","submitted_at":"2024-04-30T13:14:51Z","abstract_excerpt":"Large Language Models (LLMs) have catalyzed significant advancements in Natural Language Processing (NLP), yet they encounter challenges such as hallucination and the need for domain-specific knowledge. To mitigate these, recent methodologies have integrated information retrieved from external resources with LLMs, substantially enhancing their performance across NLP tasks. This survey paper addresses the absence of a comprehensive overview on Retrieval-Augmented Language Models (RALMs), both Retrieval-Augmented Generation (RAG) and Retrieval-Augmented Understanding (RAU), providing an in-depth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19543","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.19543/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.19543","created_at":"2026-07-05T11:28:58.990380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19543v2","created_at":"2026-07-05T11:28:58.990380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19543","created_at":"2026-07-05T11:28:58.990380+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZIGYO4DI5HB","created_at":"2026-07-05T11:28:58.990380+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZIGYO4DI5HBFXAN","created_at":"2026-07-05T11:28:58.990380+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZIGYO4D","created_at":"2026-07-05T11:28:58.990380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14222","citing_title":"Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":290,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZIGYO4DI5HBFXANI4RRBKFX2Y","json":"https://pith.science/pith/RZIGYO4DI5HBFXANI4RRBKFX2Y.json","graph_json":"https://pith.science/api/pith-number/RZIGYO4DI5HBFXANI4RRBKFX2Y/graph.json","events_json":"https://pith.science/api/pith-number/RZIGYO4DI5HBFXANI4RRBKFX2Y/events.json","paper":"https://pith.science/paper/RZIGYO4D"},"agent_actions":{"view_html":"https://pith.science/pith/RZIGYO4DI5HBFXANI4RRBKFX2Y","download_json":"https://pith.science/pith/RZIGYO4DI5HBFXANI4RRBKFX2Y.json","view_paper":"https://pith.science/paper/RZIGYO4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19543&json=true","fetch_graph":"https://pith.science/api/pith-number/RZIGYO4DI5HBFXANI4RRBKFX2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/RZIGYO4DI5HBFXANI4RRBKFX2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZIGYO4DI5HBFXANI4RRBKFX2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZIGYO4DI5HBFXANI4RRBKFX2Y/action/storage_attestation","attest_author":"https://pith.science/pith/RZIGYO4DI5HBFXANI4RRBKFX2Y/action/author_attestation","sign_citation":"https://pith.science/pith/RZIGYO4DI5HBFXANI4RRBKFX2Y/action/citation_signature","submit_replication":"https://pith.science/pith/RZIGYO4DI5HBFXANI4RRBKFX2Y/action/replication_record"}},"created_at":"2026-07-05T11:28:58.990380+00:00","updated_at":"2026-07-05T11:28:58.990380+00:00"}